agent-ledger: a security and audit plugin for Hermes Agent

说明与用途

agent-ledger 是 Hermes Agent 的本地插件，记录所有工具调用到 SQLite 日志，确认执行，检测“幽灵”调用，并根据 OWASP Agentic Top 10 对代理行为进行评分，输出 0–100 的姿态分数和发现列表。

问题

When running an AI agent locally, users trust it to edit files, restart services, and push to GitHub, but lack visibility into what the agent actually did and how risky its behavior is.

结果

The plugin provides a local, telemetry‑free audit trail of tool calls, detects ghost calls, and assigns a reproducible posture score based on OWASP criteria, enabling users to understand and mitigate agent risk.

工作流

• Clone the agent-ledger plugin into ~/.hermes/plugins/agent-ledger
• Restart the Hermes gateway to start recording tool calls
• Run python3 ~/.hermes/plugins/agent-ledger/posture.py to generate a posture report
• Optionally set up posture_daily.py with a Telegram bot token and cron for daily digests

证据

Every tool call your agent makes, recorded locally before it runs — with a 0–100 posture score and an honest list of what it can't see.

来源

When a ghost is detected, the plugin injects a warning into the agent's next context, so the agent itself goes back and verifies reality instead of trusting its memory.

来源

score = 100 − Σ{CRITICAL:25, HIGH:15, MEDIUM:8, LOW:3} over all findings, no deduplication, and the full finding list always comes back so you can recompute it by hand.

来源

The scorer ships with its full test suite, and you're encouraged to run it before trusting it: ... PASS

来源